hawhyhb/Qwen3.6-35B-A3B-Uncensored-Heretic-MTPLX-4bit-FP16

Qwen3.6-35B-A3B Uncensored Heretic · MTPLX 4-bit FP16 (+ Vision)

Local MTPLX forge of llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved, with the vision tower restored after 4-bit body conversion.

• —Body: MLX affine 4-bit (group size 64)
• —Non-quantized leaves / MTP floats: FP16 (M1/M2 friendly)
• —Vision: FP16 vision_tower.safetensors (grafted from BF16 source model.visual.*)
• —Includes mtp.safetensors + mtplx_runtime.json (verified on Apple Silicon)
• —Approx size: ~21GB on disk

Run with MTPLX

mtplx start --model hawhyhb/Qwen3.6-35B-A3B-Uncensored-Heretic-MTPLX-4bit-FP16
# or local path
mtplx start --model ~/Documents/MTPLX/models/Qwen3.6-35B-A3B-Uncensored-Heretic-MTPLX-4bit-FP16
# API only
mtplx quickstart --model hawhyhb/Qwen3.6-35B-A3B-Uncensored-Heretic-MTPLX-4bit-FP16 --profile sustained --port 8000

Vision works via OpenAI-compatible image_url content parts (no llama.cpp mmproj).

Notes

• —First forge pass dropped the vision tower; this revision grafts it back and ships preprocessor_config.json / processor_config.json / video_preprocessor_config.json.
• —Uncensored Heretic text behavior comes from the source repo; use responsibly.